@inproceedings{zhang-etal-2026-locate,
    title = "Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models",
    author = "Zhang, Hengyuan  and
      Zhang, Zhihao  and
      Nie, Ercong  and
      Wang, Mingyang  and
      Su, Zunhai  and
      Wang, Yiwei  and
      Wang, Qianli  and
      Yuan, Shuzhou  and
      Duan, Xufeng  and
      Xue, Qibo  and
      Yu, Zeping  and
      Shang, Chenming  and
      Liang, Xiao  and
      Xiong, Jing  and
      Shen, Hui  and
      Tao, Chaofan  and
      Liu, Zhengwu  and
      Jin, Senjie  and
      Xi, Zhiheng  and
      Zhang, Dongdong  and
      Ananiadou, Sophia  and
      Gui, Tao  and
      Xie, Ruobing  and
      So, Hayden Kwok-Hay  and
      Schuetze, Hinrich  and
      Huang, Xuanjing  and
      Zhang, Qi  and
      Wong, Ngai",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.502/",
    pages = "10317--10362",
    ISBN = "979-8-89176-395-1",
    abstract = "Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the opaque decision-making of Large Language Models (LLMs). However, existing reviews primarily treat MI as an observational science, summarizing analytical insights while lacking a systematic framework for actionable intervention. To bridge this gap, we present a practical survey structured around the pipeline: ``Locate, Steer, and Improve.'' We formally categorize Localizing (diagnosis) and Steering (intervention) methods based on specific Interpretable Objects to establish a rigorous intervention protocol. Furthermore, we demonstrate how this framework enables tangible improvements in Alignment, Capability, and Efficiency, effectively operationalizing MI as a practical engineering toolkit for model optimization. The curated paper list of this work is available at https://anonymous.4open.science/r/Act-MI-F068."
}